144 citations · 442 across the 24 of their papers we have counts for
11 papers · 1 filter
FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift
Huy Q. Le, Loc X. Nguyen, Yu Qiao +3
Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in…
Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence
Yu Qiao, Apurba Adhikary, Huy Q. Le +3
Federated learning (FL) has gained significant attention for enabling decentralized training on edge networks without exposing raw data. However, FL models remain susceptible to ad…
Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks
Yu Qiao, Apurba Adhikary, Kitae Kim +3
Federated learning (FL) is a distributed training technology that enhances data privacy in mobile edge networks by allowing data owners to collaborate without transmitting raw data…
Boosting Federated Domain Generalization: Understanding the Role of Advanced Pre-Trained Architectures
Avi Deb Raha, Apurba Adhikary, Mrityunjoy Gain +2
In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Gener…
FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity
Yu Qiao, Huy Q. Le, Mengchun Zhang +3
Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge…
Towards Robust Federated Learning via Logits Calibration on Non-IID Data
Yu Qiao, Apurba Adhikary, Chaoning Zhang +1
Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent stud…
Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape
Chaoning Zhang, Yu Qiao, Shehbaz Tariq +5
In contrast to the human vision that mainly depends on the shape for recognizing the objects, deep image recognition models are widely known to be biased toward texture. Recently,…
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
Chaoning Zhang, Dongshen Han, Yu Qiao +4
Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like im…
Robustness of SAM: Segment Anything Under Corruptions and Beyond
Yu Qiao, Chaoning Zhang, Taegoo Kang +3
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance…
A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
Chaoning Zhang, Joseph Cho, Fachrina Dewi Puspitasari +11
The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentat…
Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected
Dongsheng Han, Chaoning Zhang, Yu Qiao +5
Meta AI Research has recently released SAM (Segment Anything Model) which is trained on a large segmentation dataset of over 1 billion masks. As a foundation model in the field of…